© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63019
    Prev
    Next
    INDEX
    Explanations

    family structures and mathematical equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igan
    -0.08
    oop
    -0.07
    èį£
    -0.06
    æ°¸
    -0.06
     gross
    -0.06
    æĽ¼
    -0.06
    å¦ĩ
    -0.06
     Gross
    -0.06
    ikan
    -0.06
    ä¸Ļ
    -0.05
    POSITIVE LOGITS
     varying
    0.10
    åħ¨ç³»åĪĹ
    0.09
    Depending
    0.09
    vary
    0.09
     multis
    0.08
    è¿ĶåĽŀåĪĹ表
    0.08
     general
    0.08
     Depending
    0.08
     generalize
    0.08
     family
    0.08
    Activations Density 0.085%

    No Known Activations